Related papers: Resolving the Identity Crisis in Text-to-Image Gen…

Person re-identification (re-id) remains challenging due to significant intra-class variations across different cameras. Recently, there has been a growing interest in using generative models to augment training data and enhance the…

Recent advancements in diffusion models have showcased their impressive capacity to generate visually striking images. Nevertheless, ensuring a close match between the generated image and the given prompt remains a persistent challenge. In…

Recent advances in generative modeling have enabled the generation of high-quality synthetic data that is applicable in a variety of domains, including face recognition. Here, state-of-the-art generative models typically rely on…

Despite remarkable progress in Text-to-Image models, many real-world applications require generating coherent image sets with diverse consistency requirements. Existing consistent methods often focus on a specific domain with specific…

State-of-the-art generative text-to-image models are known to exhibit social biases and over-represent certain groups like people of perceived lighter skin tones and men in their outcomes. In this work, we propose a method to mitigate such…

Personalized text-to-image generation using diffusion models has recently emerged and garnered significant interest. This task learns a novel concept (e.g., a unique toy), illustrated in a handful of images, into a generative model that…

The In-context generation paradigm recently has demonstrated strong power in instructional image editing with both data efficiency and synthesis quality. Nevertheless, shaping such in-context learning for instruction-based video editing is…

The conventional training approach for image captioning involves pre-training a network using teacher forcing and subsequent fine-tuning with Self-Critical Sequence Training to maximize hand-crafted captioning metrics. However, when…

Person re-identification (Re-ID) in real-world scenarios usually suffers from various degradation factors, e.g., low-resolution, weak illumination, blurring and adverse weather. On the one hand, these degradations lead to severe…

Text-to-image (T2I) generative models have recently emerged as a powerful tool, enabling the creation of photo-realistic images and giving rise to a multitude of applications. However, the effective integration of T2I models into…

Diffusion-based text-to-image personalization have achieved great success in generating subjects specified by users among various contexts. Even though, existing finetuning-based methods still suffer from model overfitting, which greatly…

We propose a novel framework for ID-preserving generation using a multi-modal encoding strategy rather than injecting identity features via adapters into pre-trained models. Our method treats identity and text as a unified conditioning…

Recently, extensive research on image customization (e.g., identity, subject, style, background, etc.) demonstrates strong customization capabilities in large-scale generative models. However, most approaches are designed for specific…

Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data. However, this often inadvertently leads to the generation of harmful or inappropriate content and raises copyright concerns.…

Personalized text-to-image (T2I) generation has emerged as a key application for creating user-specific concepts from a few reference images. The core challenge is concept disentanglement: separating the target concept from irrelevant…

Large-scale text-to-image diffusion models have achieved great success in synthesizing high-quality and diverse images given target text prompts. Despite the revolutionary image generation ability, current state-of-the-art models still…

In controllable image generation, synthesizing coherent and consistent images from multiple reference inputs, i.e., Multi-Image Composition (MICo), remains a challenging problem, partly hindered by the lack of high-quality training data. To…

Real-World Image Super-Resolution is one of the most challenging task in image restoration. However, existing methods struggle with an accurate understanding of degraded image content, leading to reconstructed results that are both…

Text-to-image generation models that generate images based on prompt descriptions have attracted an increasing amount of attention during the past few months. Despite their encouraging performance, these models raise concerns about the…

Diffusion models are a class of flexible generative models trained with an approximation to the log-likelihood objective. However, most use cases of diffusion models are not concerned with likelihoods, but instead with downstream objectives…